The Agent Skills Directory

[SAFE]: The skill logic is transparent and focused on developer workflow automation. It resolves planning artifacts from the expected project directory (.turbo/) and applies review criteria from internal reference files. No suspicious network operations, credential exposure, or unauthorized data access patterns were identified.
[NO_CODE]: The skill is implemented purely through Markdown instructions and reference criteria documents. It does not include any executable scripts (Python, JavaScript, Shell), which minimizes the security risk and potential for malicious behavior.

review-plan